[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72Z78W7BECCZRDTYREG8FX7":3,"skill-same:01M72Z78W7BECCZRDTYREG8FX7":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M72Z78W7BECCZRDTYREG8FX7","agent-payment-x402",null,"Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments \u002F OKX Agent Payments Protocol.","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Fagent-payment-x402\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: agent-payment-x402\ndescription: Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments \u002F OKX Agent Payments Protocol.\norigin: community\n---\n\n# Agent Payment Execution (x402)\n\nEnable AI agents to make policy-gated payments with built-in spending controls. Uses the x402 HTTP payment protocol and MCP tools so agents can pay for external services, APIs, or other agents without custodial risk.\n\n## When to Use\n\nUse when: your agent needs to pay for an API call, purchase a service, settle with another agent, enforce per-task spending limits, or manage a non-custodial wallet. Pairs naturally with cost-aware-llm-pipeline and security-review skills.\n\n## Decision Tree\n\nChoose the integration path based on whether your agent is buying access to a paid API or charging others for one:\n\n| Need | Recommended path |\n|------|------------------|\n| Agent pays a 402-gated API on Base or another agentwallet-supported chain | Use `agentwallet-sdk` as an MCP payment server with strict spending policy |\n| Agent pays a 402-gated API on X Layer | Use OKX Agent Payments Protocol from `okx\u002Fonchainos-skills`; `okx-x402-payment` is a deprecated legacy alias |\n| TypeScript API charges agents | Use OKX Payments TypeScript seller SDK docs for Express, Hono, Fastify, or Next.js |\n| Go API charges agents | Use OKX Payments Go seller SDK docs for Gin, Echo, or `net\u002Fhttp` |\n| Rust API charges agents | Use OKX Payments Rust seller SDK docs for Axum |\n| Java API charges agents | Use OKX Payments Java seller SDK docs for Spring Boot 2\u002F3, Java EE, or Jakarta |\n| Python API charges agents | Check the current OKX Payments repository before implementation; a Python seller guide may not be available |\n\n## Supported Networks\n\n- `agentwallet-sdk`: use the package docs to confirm current network coverage before production. Base Sepolia is the safest development default; Base mainnet is the production path called out by the original skill.\n- OKX Payments \u002F X Layer: current seller docs target X Layer (`eip155:196`) and USDT0 settlement. Fetch current SDK docs before generating production code because payment packages and facilitator behavior can change quickly.\n\n## How It Works\n\n### x402 Protocol\nx402 extends HTTP 402 (Payment Required) into a machine-negotiable flow. When a server returns `402`, the agent's payment tool negotiates price, checks budget, signs a transaction, and retries only inside the policy and confirmation boundary set by the orchestrator.\n\n### Spending Controls\nEvery payment tool call enforces a `SpendingPolicy`:\n- **Per-task budget** — max spend for a single agent action\n- **Per-session budget** — cumulative limit across an entire session\n- **Allowlisted recipients** — restrict which addresses\u002Fservices the agent can pay\n- **Rate limits** — max transactions per minute\u002Fhour\n\n### Non-Custodial Wallets\nAgents hold their own keys via ERC-4337 smart accounts. The orchestrator sets policy before delegation; the agent can only spend within bounds. No pooled funds, no custodial risk.\n\n## MCP Integration\n\nThe payment layer exposes standard MCP tools that slot into any Claude Code or agent harness setup.\n\n> **Security note**: Always pin the package version. This tool manages private keys — unpinned `npx` installs introduce supply-chain risk.\n\n### Option A: agentwallet-sdk (Base \u002F multi-chain)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentpay\": {\n      \"command\": \"npx\",\n      \"args\": [\"agentwallet-sdk@6.0.0\"]\n    }\n  }\n}\n```\n\n### Available Tools (agent-callable)\n\n| Tool | Purpose |\n|------|---------|\n| `get_balance` | Check agent wallet balance |\n| `send_payment` | Send payment to address or ENS |\n| `check_spending` | Query remaining budget |\n| `list_transactions` | Audit trail of all payments |\n\n> **Note**: Spending policy is set by the **orchestrator** before delegating to the agent — not by the agent itself. This prevents agents from escalating their own spending limits. Configure policy via `set_policy` in your orchestration layer or pre-task hook, never as an agent-callable tool.\n\n### Option B: OKX Agent Payments Protocol (X Layer)\n\nUse this path for X Layer x402, Multi-Party Payment (MPP), session payment, charge, and A2A charge flows.\n\nFor buyer-side agent flows:\n\n1. Install or reference the current `okx\u002Fonchainos-skills` repository.\n2. Use `skills\u002Fokx-agent-payments-protocol\u002FSKILL.md` as the dispatcher.\n3. Treat `skills\u002Fokx-x402-payment\u002FSKILL.md` as a deprecated compatibility alias, not as the canonical skill.\n4. Require explicit user confirmation before wallet status checks or payment actions. Do not hide payment execution behind a generic tool call.\n\nFor seller-side API flows, fetch the latest language-specific guide before generating code:\n\n| Runtime | Current guide |\n|---------|---------------|\n| TypeScript | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Ftypescript\u002FSELLER.md` |\n| Go | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Fgo\u002Fx402\u002FSELLER.md` |\n| Rust | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Frust\u002Fx402\u002FSELLER.md` |\n| Java | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Fjava\u002FSELLER.md` |\n\nDo not copy examples from older docs without checking the current OKX repository. Current OKX guidance uses `okx-agent-payments-protocol` as the dispatcher, and Java seller docs are now available.\n\n## Examples\n\n### Budget enforcement in an MCP client\n\nWhen building an orchestrator that calls the agentpay MCP server, enforce budgets before dispatching paid tool calls.\n\n> **Prerequisites**: Install the package before adding the MCP config — `npx` without `-y` will prompt for confirmation in non-interactive environments, causing the server to hang: `npm install -g agentwallet-sdk@6.0.0`\n\n```typescript\nimport { Client } from \"@modelcontextprotocol\u002Fsdk\u002Fclient\u002Findex.js\";\nimport { StdioClientTransport } from \"@modelcontextprotocol\u002Fsdk\u002Fclient\u002Fstdio.js\";\n\nasync function main() {\n  \u002F\u002F 1. Validate credentials before constructing the transport.\n  \u002F\u002F    A missing key must fail immediately — never let the subprocess start without auth.\n  const walletKey = process.env.WALLET_PRIVATE_KEY;\n  if (!walletKey) {\n    throw new Error(\"WALLET_PRIVATE_KEY is not set — refusing to start payment server\");\n  }\n\n  \u002F\u002F Connect to the agentpay MCP server via stdio transport.\n  \u002F\u002F Whitelist only the env vars the server needs — never forward all of process.env\n  \u002F\u002F to a third-party subprocess that manages private keys.\n  const transport = new StdioClientTransport({\n    command: \"npx\",\n    args: [\"agentwallet-sdk@6.0.0\"],\n    env: {\n      PATH: process.env.PATH ?? \"\",\n      NODE_ENV: process.env.NODE_ENV ?? \"production\",\n      WALLET_PRIVATE_KEY: walletKey,\n    },\n  });\n  const agentpay = new Client({ name: \"orchestrator\", version: \"1.0.0\" });\n  await agentpay.connect(transport);\n\n  \u002F\u002F 2. Set spending policy before delegating to the agent.\n  \u002F\u002F    Always verify success — a silent failure means no controls are active.\n  const policyResult = await agentpay.callTool({\n    name: \"set_policy\",\n    arguments: {\n      per_task_budget: 0.50,\n      per_session_budget: 5.00,\n      allowlisted_recipients: [\"api.example.com\"],\n    },\n  });\n  if (policyResult.isError) {\n    throw new Error(\n      `Failed to set spending policy — do not delegate: ${JSON.stringify(policyResult.content)}`\n    );\n  }\n\n  \u002F\u002F 3. Use preToolCheck before any paid action\n  await preToolCheck(agentpay, 0.01);\n}\n\n\u002F\u002F Pre-tool hook: fail-closed budget enforcement with four distinct error paths.\nasync function preToolCheck(agentpay: Client, apiCost: number): Promise\u003Cvoid> {\n  \u002F\u002F Path 1: Reject invalid input (NaN\u002FInfinity bypass the \u003C comparison)\n  if (!Number.isFinite(apiCost) || apiCost \u003C 0) {\n    throw new Error(`Invalid apiCost: ${apiCost} — action blocked`);\n  }\n\n  \u002F\u002F Path 2: Transport\u002Fconnectivity failure\n  let result;\n  try {\n    result = await agentpay.callTool({ name: \"check_spending\" });\n  } catch (err) {\n    throw new Error(`Payment service unreachable — action blocked: ${err}`);\n  }\n\n  \u002F\u002F Path 3: Tool returned an error (e.g., auth failure, wallet not initialised)\n  if (result.isError) {\n    throw new Error(\n      `check_spending failed — action blocked: ${JSON.stringify(result.content)}`\n    );\n  }\n\n  \u002F\u002F Path 4: Parse and validate the response shape\n  let remaining: number;\n  try {\n    const parsed = JSON.parse(\n      (result.content as Array\u003C{ text: string }>)[0].text\n    );\n    if (!Number.isFinite(parsed?.remaining)) {\n      throw new TypeError(\"missing or non-finite 'remaining' field\");\n    }\n    remaining = parsed.remaining;\n  } catch (err) {\n    throw new Error(\n      `check_spending returned unexpected format — action blocked: ${err}`\n    );\n  }\n\n  \u002F\u002F Path 5: Budget exceeded\n  if (remaining \u003C apiCost) {\n    throw new Error(\n      `Budget exceeded: need $${apiCost} but only $${remaining} remaining`\n    );\n  }\n}\n\nmain().catch((err) => {\n  console.error(err);\n  process.exitCode = 1;\n});\n```\n\n## Best Practices\n\n- **Set budgets before delegation**: When spawning sub-agents, attach a SpendingPolicy via your orchestration layer. Never give an agent unlimited spend.\n- **Pin your dependencies**: Always specify an exact version in your MCP config (e.g., `agentwallet-sdk@6.0.0`). Verify package integrity before deploying to production.\n- **Audit trails**: Use `list_transactions` in post-task hooks to log what was spent and why.\n- **Fail closed**: If the payment tool is unreachable, block the paid action — don't fall back to unmetered access.\n- **Pair with security-review**: Payment tools are high-privilege. Apply the same scrutiny as shell access.\n- **Test with testnets first**: Use Base Sepolia for development; switch to Base mainnet for production.\n\n## Production Reference\n\n- **npm**: [`agentwallet-sdk`](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fagentwallet-sdk)\n- **Merged into NVIDIA NeMo Agent Toolkit**: [PR #17](https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNeMo-Agent-Toolkit-Examples\u002Fpull\u002F17) — x402 payment tool for NVIDIA's agent examples\n- **Protocol spec**: [x402.org](https:\u002F\u002Fx402.org)\n- **OKX Payments SDKs**: [`okx\u002Fpayments`](https:\u002F\u002Fgithub.com\u002Fokx\u002Fpayments) — TypeScript, Go, Rust, and Java seller integrations for X Layer x402\n- **OKX Agent Payments Protocol skill**: [`okx\u002Fonchainos-skills`](https:\u002F\u002Fgithub.com\u002Fokx\u002Fonchainos-skills\u002Ftree\u002Fmain\u002Fskills\u002Fokx-agent-payments-protocol)\n- **OKX Payments overview**: [web3.okx.com\u002Fonchainos\u002Fdev-docs\u002Fpayments\u002Foverview](https:\u002F\u002Fweb3.okx.com\u002Fonchainos\u002Fdev-docs\u002Fpayments\u002Foverview)\n","# Agent Payment Execution (x402)\n\nEnable AI agents to make policy-gated payments with built-in spending controls. Uses the x402 HTTP payment protocol and MCP tools so agents can pay for external services, APIs, or other agents without custodial risk.\n\n## When to Use\n\nUse when: your agent needs to pay for an API call, purchase a service, settle with another agent, enforce per-task spending limits, or manage a non-custodial wallet. Pairs naturally with cost-aware-llm-pipeline and security-review skills.\n\n## Decision Tree\n\nChoose the integration path based on whether your agent is buying access to a paid API or charging others for one:\n\n| Need | Recommended path |\n|------|------------------|\n| Agent pays a 402-gated API on Base or another agentwallet-supported chain | Use `agentwallet-sdk` as an MCP payment server with strict spending policy |\n| Agent pays a 402-gated API on X Layer | Use OKX Agent Payments Protocol from `okx\u002Fonchainos-skills`; `okx-x402-payment` is a deprecated legacy alias |\n| TypeScript API charges agents | Use OKX Payments TypeScript seller SDK docs for Express, Hono, Fastify, or Next.js |\n| Go API charges agents | Use OKX Payments Go seller SDK docs for Gin, Echo, or `net\u002Fhttp` |\n| Rust API charges agents | Use OKX Payments Rust seller SDK docs for Axum |\n| Java API charges agents | Use OKX Payments Java seller SDK docs for Spring Boot 2\u002F3, Java EE, or Jakarta |\n| Python API charges agents | Check the current OKX Payments repository before implementation; a Python seller guide may not be available |\n\n## Supported Networks\n\n- `agentwallet-sdk`: use the package docs to confirm current network coverage before production. Base Sepolia is the safest development default; Base mainnet is the production path called out by the original skill.\n- OKX Payments \u002F X Layer: current seller docs target X Layer (`eip155:196`) and USDT0 settlement. Fetch current SDK docs before generating production code because payment packages and facilitator behavior can change quickly.\n\n## How It Works\n\n### x402 Protocol\nx402 extends HTTP 402 (Payment Required) into a machine-negotiable flow. When a server returns `402`, the agent's payment tool negotiates price, checks budget, signs a transaction, and retries only inside the policy and confirmation boundary set by the orchestrator.\n\n### Spending Controls\nEvery payment tool call enforces a `SpendingPolicy`:\n- **Per-task budget** — max spend for a single agent action\n- **Per-session budget** — cumulative limit across an entire session\n- **Allowlisted recipients** — restrict which addresses\u002Fservices the agent can pay\n- **Rate limits** — max transactions per minute\u002Fhour\n\n### Non-Custodial Wallets\nAgents hold their own keys via ERC-4337 smart accounts. The orchestrator sets policy before delegation; the agent can only spend within bounds. No pooled funds, no custodial risk.\n\n## MCP Integration\n\nThe payment layer exposes standard MCP tools that slot into any Claude Code or agent harness setup.\n\n> **Security note**: Always pin the package version. This tool manages private keys — unpinned `npx` installs introduce supply-chain risk.\n\n### Option A: agentwallet-sdk (Base \u002F multi-chain)\n\n```json\n{\n  \"mcpServers\": {\n    \"agentpay\": {\n      \"command\": \"npx\",\n      \"args\": [\"agentwallet-sdk@6.0.0\"]\n    }\n  }\n}\n```\n\n### Available Tools (agent-callable)\n\n| Tool | Purpose |\n|------|---------|\n| `get_balance` | Check agent wallet balance |\n| `send_payment` | Send payment to address or ENS |\n| `check_spending` | Query remaining budget |\n| `list_transactions` | Audit trail of all payments |\n\n> **Note**: Spending policy is set by the **orchestrator** before delegating to the agent — not by the agent itself. This prevents agents from escalating their own spending limits. Configure policy via `set_policy` in your orchestration layer or pre-task hook, never as an agent-callable tool.\n\n### Option B: OKX Agent Payments Protocol (X Layer)\n\nUse this path for X Layer x402, Multi-Party Payment (MPP), session payment, charge, and A2A charge flows.\n\nFor buyer-side agent flows:\n\n1. Install or reference the current `okx\u002Fonchainos-skills` repository.\n2. Use `skills\u002Fokx-agent-payments-protocol\u002FSKILL.md` as the dispatcher.\n3. Treat `skills\u002Fokx-x402-payment\u002FSKILL.md` as a deprecated compatibility alias, not as the canonical skill.\n4. Require explicit user confirmation before wallet status checks or payment actions. Do not hide payment execution behind a generic tool call.\n\nFor seller-side API flows, fetch the latest language-specific guide before generating code:\n\n| Runtime | Current guide |\n|---------|---------------|\n| TypeScript | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Ftypescript\u002FSELLER.md` |\n| Go | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Fgo\u002Fx402\u002FSELLER.md` |\n| Rust | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Frust\u002Fx402\u002FSELLER.md` |\n| Java | `https:\u002F\u002Fraw.githubusercontent.com\u002Fokx\u002Fpayments\u002Fmain\u002Fjava\u002FSELLER.md` |\n\nDo not copy examples from older docs without checking the current OKX repository. Current OKX guidance uses `okx-agent-payments-protocol` as the dispatcher, and Java seller docs are now available.\n\n## Examples\n\n### Budget enforcement in an MCP client\n\nWhen building an orchestrator that calls the agentpay MCP server, enforce budgets before dispatching paid tool calls.\n\n> **Prerequisites**: Install the package before adding the MCP config — `npx` without `-y` will prompt for confirmation in non-interactive environments, causing the server to hang: `npm install -g agentwallet-sdk@6.0.0`\n\n```typescript\nimport { Client } from \"@modelcontextprotocol\u002Fsdk\u002Fclient\u002Findex.js\";\nimport { StdioClientTransport } from \"@modelcontextprotocol\u002Fsdk\u002Fclient\u002Fstdio.js\";\n\nasync function main() {\n  \u002F\u002F 1. Validate credentials before constructing the transport.\n  \u002F\u002F    A missing key must fail immediately — never let the subprocess start without auth.\n  const walletKey = process.env.WALLET_PRIVATE_KEY;\n  if (!walletKey) {\n    throw new Error(\"WALLET_PRIVATE_KEY is not set — refusing to start payment server\");\n  }\n\n  \u002F\u002F Connect to the agentpay MCP server via stdio transport.\n  \u002F\u002F Whitelist only the env vars the server needs — never forward all of process.env\n  \u002F\u002F to a third-party subprocess that manages private keys.\n  const transport = new StdioClientTransport({\n    command: \"npx\",\n    args: [\"agentwallet-sdk@6.0.0\"],\n    env: {\n      PATH: process.env.PATH ?? \"\",\n      NODE_ENV: process.env.NODE_ENV ?? \"production\",\n      WALLET_PRIVATE_KEY: walletKey,\n    },\n  });\n  const agentpay = new Client({ name: \"orchestrator\", version: \"1.0.0\" });\n  await agentpay.connect(transport);\n\n  \u002F\u002F 2. Set spending policy before delegating to the agent.\n  \u002F\u002F    Always verify success — a silent failure means no controls are active.\n  const policyResult = await agentpay.callTool({\n    name: \"set_policy\",\n    arguments: {\n      per_task_budget: 0.50,\n      per_session_budget: 5.00,\n      allowlisted_recipients: [\"api.example.com\"],\n    },\n  });\n  if (policyResult.isError) {\n    throw new Error(\n      `Failed to set spending policy — do not delegate: ${JSON.stringify(policyResult.content)}`\n    );\n  }\n\n  \u002F\u002F 3. Use preToolCheck before any paid action\n  await preToolCheck(agentpay, 0.01);\n}\n\n\u002F\u002F Pre-tool hook: fail-closed budget enforcement with four distinct error paths.\nasync function preToolCheck(agentpay: Client, apiCost: number): Promise\u003Cvoid> {\n  \u002F\u002F Path 1: Reject invalid input (NaN\u002FInfinity bypass the \u003C comparison)\n  if (!Number.isFinite(apiCost) || apiCost \u003C 0) {\n    throw new Error(`Invalid apiCost: ${apiCost} — action blocked`);\n  }\n\n  \u002F\u002F Path 2: Transport\u002Fconnectivity failure\n  let result;\n  try {\n    result = await agentpay.callTool({ name: \"check_spending\" });\n  } catch (err) {\n    throw new Error(`Payment service unreachable — action blocked: ${err}`);\n  }\n\n  \u002F\u002F Path 3: Tool returned an error (e.g., auth failure, wallet not initialised)\n  if (result.isError) {\n    throw new Error(\n      `check_spending failed — action blocked: ${JSON.stringify(result.content)}`\n    );\n  }\n\n  \u002F\u002F Path 4: Parse and validate the response shape\n  let remaining: number;\n  try {\n    const parsed = JSON.parse(\n      (result.content as Array\u003C{ text: string }>)[0].text\n    );\n    if (!Number.isFinite(parsed?.remaining)) {\n      throw new TypeError(\"missing or non-finite 'remaining' field\");\n    }\n    remaining = parsed.remaining;\n  } catch (err) {\n    throw new Error(\n      `check_spending returned unexpected format — action blocked: ${err}`\n    );\n  }\n\n  \u002F\u002F Path 5: Budget exceeded\n  if (remaining \u003C apiCost) {\n    throw new Error(\n      `Budget exceeded: need $${apiCost} but only $${remaining} remaining`\n    );\n  }\n}\n\nmain().catch((err) => {\n  console.error(err);\n  process.exitCode = 1;\n});\n```\n\n## Best Practices\n\n- **Set budgets before delegation**: When spawning sub-agents, attach a SpendingPolicy via your orchestration layer. Never give an agent unlimited spend.\n- **Pin your dependencies**: Always specify an exact version in your MCP config (e.g., `agentwallet-sdk@6.0.0`). Verify package integrity before deploying to production.\n- **Audit trails**: Use `list_transactions` in post-task hooks to log what was spent and why.\n- **Fail closed**: If the payment tool is unreachable, block the paid action — don't fall back to unmetered access.\n- **Pair with security-review**: Payment tools are high-privilege. Apply the same scrutiny as shell access.\n- **Test with testnets first**: Use Base Sepolia for development; switch to Base mainnet for production.\n\n## Production Reference\n\n- **npm**: [`agentwallet-sdk`](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fagentwallet-sdk)\n- **Merged into NVIDIA NeMo Agent Toolkit**: [PR #17](https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNeMo-Agent-Toolkit-Examples\u002Fpull\u002F17) — x402 payment tool for NVIDIA's agent examples\n- **Protocol spec**: [x402.org](https:\u002F\u002Fx402.org)\n- **OKX Payments SDKs**: [`okx\u002Fpayments`](https:\u002F\u002Fgithub.com\u002Fokx\u002Fpayments) — TypeScript, Go, Rust, and Java seller integrations for X Layer x402\n- **OKX Agent Payments Protocol skill**: [`okx\u002Fonchainos-skills`](https:\u002F\u002Fgithub.com\u002Fokx\u002Fonchainos-skills\u002Ftree\u002Fmain\u002Fskills\u002Fokx-agent-payments-protocol)\n- **OKX Payments overview**: [web3.okx.com\u002Fonchainos\u002Fdev-docs\u002Fpayments\u002Foverview](https:\u002F\u002Fweb3.okx.com\u002Fonchainos\u002Fdev-docs\u002Fpayments\u002Foverview)\n",{"name":5,"origin":24,"description":7},"community","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","skills\u002Fagent-payment-x402",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill agent-payment-x402",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill agent-payment-x402",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill agent-payment-x402","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Fagent-payment-x402\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7325TFQF1DZTQ6J3WGQQ1VR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]